Keras2ncnn Release v0.2.0

THIS RELEASE CONTAINS MULTIPLE CRITICAL UPDATES, PLACE UPGRADE YOUR LOCAL VERSION BEFORE USE.

#Linux and Mac
python3 -mpip install --upgrade keras2ncnn

#Windows
py.exe -mpip install --upgrade keras2ncnn

NEW OPS:
#40 Support TanH activation for Dense Op

BUG FIX:
#38 [CRITICAL] When converting fused relu6, clip may not be inserted
#39 Support old Keras version descriptor
#41 [CRITICAL] The param table may be modified unexpectedly during the conversion.
#42 [CRITICAL] Emitting BinaryOp with more than two inputs.

Keras2ncnn Release v0.1.7

NEW OPS:
#24 Add support to SeparableConv2D and BilinearUpsampling 27cc153
#27 Add support to Relu6 Activation 943cd5c
#33 Add support to Permute ad6ab22
Add support to decoding Functional c6db96e

BUG FIX:
#30 When there is only one layer, the optimizer thought it was a dummy node and removed 87357b0
Remove redundant InputLayer when using a sequential model. fbabcad

Keras2ncnn Release v0.1.5

BUG FIX:

• #23 Add support to SeparableConv2D. ce4c1c8
• #22 Fix "'str' object has no attribute 'decode'" on certain python version. 9980e9a
• #21 Add limited support to TensorflowOpLayer (Mul with constant). 71dbf08

Keras2ncnn Release v0.1.4

BUG FIX:
#18 Emit default input when no input layer is specific in Keras.
Fix a byte string decoding bug on certain version of h5py.

NEW FEATURES:
MUCH MUCH BETTER Exception Prints. If you meet any issue, attach the exception message will help a lot!

Keras2ncnn Release v0.1.3

BUG FIX:

• Fix a bug in reshape. When using reshape as squeeze, the dim is incorrect.
• Fix a bug in ReLU layer. When ReLU does not have slopt, the converter will throw an error.

NEW FEATURES:

• Better debugging system! Try it out when you converting yout model by ->

python3 -m keras2ncnn -i YOUT_KERAS_FILE.h5 -d

KNOWN BUGS:

• The debugger does not work well with multi out or multi input model.
• The debugger is WIP, so... It will have a lot of bugs.

Keras2ncnn Release v0.1.2

BUG FIX:

• When emitting fused sigmoid for Dense layer, an extra softmax layer may be inserted after the Dense layer.
• When parsing nested sequential graph, the joint of the the graph may be misconnected.

NEW FEATURES:

• New debugging system allowing for ease comparing accuracy between ncnn and keras graph.

Keras2ncnn Release v0.1.1

Feature Highlights

• Keras h5df to ncnn param/bin file converter
• Support a variety of models, sequential or not, TF1 or TF2 !
• New weight indexing method, better model compatibility !
• Emended debugger for comparing accuracy with ncnn. (Working on)

Supported Op

• InputLayer
• Conv2D (With fused relu, sigmoid activation)
• Conv2DTranspose (With fused relu, sigmoid activation)
• DepthwiseConv2D
• Add
• Multiply
• ZeroPadding2D
• ReLU
• LeakyReLU
• UpSampling2D
• Concatenate
• GlobalAveragePooling2D
• MaxAveragePooling2D
• AveragePooling2D
• MaxPooling2D
• BatchNormalization
• Dense (With fused relu, sigmoid, and non-fused softmax activation)
• Activation (Support relu, sigmoid)